In a breakthrough that would redefine the future of computing, Chinese scientists have developed the world’s first carbon-based, totally microchip capable of running artificial intelligence tasks using a novel ternary logic device, leapfrogging today’s binary-dependent technology.
The achievement, led by researchers from Peking University and Beijing University of Posts and Telecommunications, marks a pivotal step toward next-generation semiconductors that might outperform silicon in speed, performance, and scalability.
The group unveiled a carbon nanotube (CNT) transistor chip that strategizes facts no longer simply in ones and zeros but also in a third state, enabling computations to occur quicker and with much less energy. In experiments, the chip tested flawless accuracy in photo recognition tasks, a milestone detailed in the January issue of the journal Science Advances.
CNTs are tiny cylindrical tubes crafted from graphene sheets, and they have been used in general as conductive components in lithium-ion batteries.
However, due to their superior electric conductivity, excellent balance, and ultra-thin shape, CNTs are seen as a promising material for the next generation of semiconductors.
By way of adjusting the gate voltage, the CNT transistor can transfer among three distinct current states, as a result growing the foundation for ternary logic circuits. This new design promises to overcome the limitations of current chip technologies, especially in terms of power intake and processing speed.
To test the capabilities of their new chip, the researchers built a neural network able to learn and reason by mimicking the connections between neurons in the human mind.
Extensive experiments revealed that the CNT-based neural network executed the best accuracy in classifying handwritten digits, demonstrating its great ability for AI packages, which include photograph recognition and machine learning duties.
One of the lead researchers, Peng Lianmao, a member of the Chinese Academy of Sciences, has been analyzing carbon-based chip technology for many years.
His crew has made remarkable progress in growing excessive overall performance CNTs and attaining precise control over nanotube arrays. In 2020, they fabricated an eight-inch CNT wafer that outperformed similar silicon-based devices in integrated circuit performance.
This success cemented China’s position at the forefront of global research in the carbon-primarily based semiconductor era.
The new chip isn’t only highly green but also offers high stability and strong resistance to interference, making it best to be used in excessive-performance computing, machine learning, AI, and low-power storage devices. It also has programs for Internet of Things (IoT) devices, in which energy efficiency is an essential aspect.
Read more: NUST students set to receive hands-on training in chip design
Despite the numerous advantages, carbon nanotube chips still lag traditional silicon chips in terms of integration density. As an example, Nvidia’s RTX 5090 GPU, which was introduced in January 2025, incorporates a staggering 92 billion transistors, far exceeding the modern skills of the CNT generation.
However, the improvement of carbon-based chips is viewed as the next frontier in semiconductor generation, and China is currently leading the way in this race.
Peng Lianmao expressed his optimism about the future of carbon nanotube-based chips, mentioning that the goal is to make them mainstream in the next 10 to 15 years.
If successful, this technology could replace silicon-primarily based chips in a wide variety of packages, from supercomputers and statistics centers to smartphones and different electronic devices.
This transition could mark a considerable shift within the semiconductor industry, paving the way for a brand-new generation of high-performance, low-energy computing solutions.